def divide_dataset(self):
tp = ReadFile(self.dataset, space_type=self.space_type)
tp.split_dataset()
for fold in xrange(self.n_folds):
dict_feedback = list()
tp.triple_dataset = list(set(tp.triple_dataset))
random.shuffle(tp.triple_dataset)
sp = int((1-self.test_ratio) * len(tp.triple_dataset))
train = tp.triple_dataset[:sp]
test = tp.triple_dataset[sp:]
train.sort()
test.sort(key=lambda x: x[0])
train_set = list()
test_set = list()
for i, feedback in enumerate(self.dataset):
dict_individual = dict()
for triple in train:
try:
dict_individual.setdefault(triple[0], {}).update(
{triple[1]: tp.individual_interaction[i][triple[0]][triple[1]]})
train_set.append([triple[0], triple[1], tp.individual_interaction[i][triple[0]][triple[1]]])
except KeyError:
pass
for triple_test in test:
try:
test_set.append([triple_test[0], triple_test[1],
tp.individual_interaction[i][triple_test[0]][triple_test[1]]])
except KeyError:
pass
dict_feedback.append(dict_individual)
self.dict_feedback_folds[fold] = dict_feedback
self.dict_folds[fold] = {'train': train_set, 'test': test_set}
